Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models
This work addresses the problem of creating more human-like and supportive conversational agents, representing an incremental advancement by combining specialized models with LLMs.
The paper tackles the trade-off between analytical depth and generative fluency in empathetic response generation by proposing TRACE, a framework that decomposes empathy into a structured pipeline for analysis and synthesis, resulting in significant performance improvements over baselines in automatic and LLM-based evaluations.
Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents. However, existing methods face a core trade-off between the analytical depth of specialized models and the generative fluency of Large Language Models (LLMs). To address this, we propose TRACE, Task-decomposed Reasoning for Affective Communication and Empathy, a novel framework that models empathy as a structured cognitive process by decomposing the task into a pipeline for analysis and synthesis. By building a comprehensive understanding before generation, TRACE unites deep analysis with expressive generation. Experimental results show that our framework significantly outperforms strong baselines in both automatic and LLM-based evaluations, confirming that our structured decomposition is a promising paradigm for creating more capable and interpretable empathetic agents. Our code is available at https://anonymous.4open.science/r/TRACE-18EF/README.md.